Download:
by Bailing Zhang, Minyue Fu, Hong Yan, Marwan A. Jabri
IEEE Trans. on Neural Networks
http://murray.newcastle.edu.au/users/staff/eemf/home/Papers/IEEE_TNN.pdf
Add To MetaCart
Abstract:
Abstract — The adaptive-subspace self-organizing map (AS-SOM) proposed by Kohonen is a recent development in selforganizing map (SOM) computation. In this paper, we propose a method to realize ASSOM using a neural learning algorithm in nonlinear autoencoder networks. Our method has the advantage of numerical stability. We have applied our ASSOM model to build a modular classification system for handwritten digit recognition. Ten ASSOM modules are used to capture different features in the ten classes of digits. When a test digit is presented to all the modules, each module provides a reconstructed pattern and the system outputs a class label by comparing the ten reconstruction errors. Our experiments show promising results. For relatively small size modules, the classification accuracy reaches 99.3 % on the training set and over 97 % on the testing set. Index Terms — Adaptive-subspace self-organizing map, handwritten digit recognition, principal component analysis.
Citations
|
2062
|
The Self-Organizing Map
– Kohonen
- 1990
|
|
273
|
A simplified neuron model as a principal component analyzer
– Oja
- 1982
|
|
225
|
Principal curves
– Hastie, Stuetzle
- 1989
|
|
192
|
Efficient pattern recognition using a new transformation distance
– Simard, LeCun, et al.
- 1993
|
|
164
|
Optimal unsupervised learning in a single-layer linear feedforward neural network. Neural Networks
– Sanger
- 1989
|
|
137
|
Non linear principal components analysis using auto-associative neural networks
– Kramer
- 1991
|
|
117
|
Modeling the manifolds of images of handwritten digits
– Hinton, Dayan, et al.
- 1996
|
|
75
|
Representation and separation of signals using nonlinear PCA type learning
– Karhunen, Joutsensalo
- 1994
|
|
70
|
Dimension reduction by local principal component analysis
– Kambhatla, leen
- 1997
|
|
59
|
Computer recognition of unconstrained handwritten numerals
– Suen, Nadal, et al.
- 1992
|
|
53
|
Auto-association by multilayer perceptrons and singular value decomposition
– Bourlard, Kamp
- 1988
|
|
50
|
Engineering applications of the self-organizing map
– Kohonen, Oja, et al.
- 1996
|
|
50
|
Using generative models for handwritten digit recognition
– Revow, Williams, et al.
- 1996
|
|
36
|
Least Mean Square Error Reconstruction Principle for Self-Organizing Neural-Nets”, Neural Networks
– Xu
- 1993
|
|
30
|
Self-organized formation of various invariant-feature filters
– Kohonen, Kaski, et al.
- 1997
|
|
24
|
Emergence of invariant-feature detectors in the adaptive-subspace self-organizing map
– Kohonen
- 1996
|
|
7
|
An approach to non-linear principal component analysis using radially symmetric basis functions
– Webb
- 1996
|
|
5
|
Image segmentation using a mixture of principal components representation
– Dony, Haykin
- 1997
|
|
3
|
networks, principal components and subspace
– “Neural
- 1989
|
|
1
|
of principal component analysis, optimization problems, and neural networks
– “Generalizations
- 1995
|
